Academic Deep Search

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:33 PM UTC
• Version:
  2.1.0

Overview

The available evidence shows a literature-research skill with a scope-quality concern, but no signs of hidden access, persistence, credential use, destructive actions, or exfiltration.

Before installing, check that you want a general literature-research helper to activate on broad research prompts. If you only need narrow biomedical, methods, marker, or figure-focused synthesis, tighten the invocation wording locally or use a narrower skill.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The skill’s invocation guidance is broad enough to match many generic research-help requests, which can cause inappropriate routing and overuse of this skill outside its intended niche. That creates a security and safety boundary problem: users may be funneled into literature-search behavior when a narrower or safer skill should have handled the request, increasing risk of policy bypass, unreliable source handling, or unintended external retrieval.

VirusTotal

63/63 vendors flagged this skill as clean.